Sapient Intelligence (@Sapient

Sapient Intelligence

33 posts

Sapient Intelligence

@Sapient_Int

Building efficient & powerful general intelligence through brain-inspired architecture

Palo Alto, CA

Joined July 2024

Pinned
Sapient Intelligence
@Sapient_Int
May 18
Introducing HRM-Text. An ultra-lean 1B-parameter reasoning language model designed to deliver strong general performance with a fraction of the data, compute, and infrastructure. Trained on just 40B structured tokens, HRM-Text achieves competitive performance while using
00:00
510K
Sapient Intelligence reposted
VentureBeat
@VentureBeat
Jun 10
A 1B reasoning model trained on 40B tokens — not trillions — hit benchmark scores rivaling models 7x its size. Cost: $1,500.
A $1,500 foundation model that rivals larger LLMs
From venturebeat.com
6.7K
Sapient Intelligence
@Sapient_Int
May 26
Excited to see our community building with HRM-Text! Can’t wait to see where you take it next.🚀 Whether you’re reproducing the benchmarks, testing it out in your own field, or building something entirely new, we’d love to hear about it. Drop your ideas, questions, and
3.2K
Sapient Intelligence
@Sapient_Int
May 19
In this benchmark deep-dive, Sapient’s founders William and Guan are joined by research team members Changling and Yasin to unpack HRM-Text’s performance across MATH, DROP, ARC-Challenge, and MMLU. 📊 Beyond the scores, they discuss what each benchmark measures, how HRM-Text
00:00
241K
Sapient Intelligence
@Sapient_Int
May 22
Paper: arxiv.org/abs/2605.20613 GitHub: github.com/sapientinc/HRM… Hugging Face: huggingface.co/sapientinc/HRM…
arxiv.org
HRM-Text: Efficient Pretraining Beyond Scaling
The current pretraining paradigm for large language models relies on massive compute and internet-scale raw text, creating a significant barrier to foundational research. In contrast, biological...
665
Sapient Intelligence
@Sapient_Int
May 22
Replying to @Sapient_Int
Paper:
arxiv.org
HRM-Text: Efficient Pretraining Beyond Scaling
The current pretraining paradigm for large language models relies on massive compute and internet-scale raw text, creating a significant barrier to foundational research. In contrast, biological...
950
Sapient Intelligence reposted
Guan Wang
@makingAGI
May 20
The HRM-Text paper is now available 🎉 HRM-Text explores a different approach to language model pretraining: hierarchical recurrent computation, task-completion training, and latent-space reasoning. At just 1B parameters, HRM-Text achieves competitive performance with
89K
Sapient Intelligence
@Sapient_Int
May 19
HRM-Text 101 is here. This tutorial takes you from zero to one: from setup to fine-tuning to evaluation. Download the base checkpoint. Fine-tune it on a real task. Evaluate the results. End to end, on a single GPU. Watch the tutorial and start building with HRM-Text.
00:00
187K
Sapient Intelligence
@Sapient_Int
May 19
Download HRM-Text🔗 GitHub: github.com/sapientinc/HRM… Hugging Face: huggingface.co/sapientinc/HRM…
GitHub - sapientinc/HRM-Text: HRM-Text is a 1B text generation model based on the HRM architecture,...
From github.com
3.5K
Sapient Intelligence
@Sapient_Int
May 18
Replying to @Sapient_Int
Download HRM-Text 🔗 Github: github.com/sapientinc/HRM… Hugging Face: huggingface.co/sapientinc/HRM…
GitHub - sapientinc/HRM-Text: HRM-Text is a 1B text generation model based on the HRM architecture,...
From github.com
36K
Sapient Intelligence
@Sapient_Int
May 18
Tomorrow, we will unveil a new path to general intelligence. Lean. Powerful. Efficient. The countdown is on⏳
46K
Sapient Intelligence
@Sapient_Int
May 16
It is time to liberate reasoning from language! HRM (Hierarchical Reasoning Model) takes a simple idea from the brain: separating reasoning (thinking) from language. When we think, our brains process information in high-dimensional, abstract streams--deep, instantaneous, and
2.7K
Sapient Intelligence
@Sapient_Int
May 13
Is bigger always better in AI? 🧠 We've reached incredible SOTAs by brute-forcing scale with astronomical token counts. But consider the human brain: running on just 20W of power and trained on ~1B language tokens, it's still making miracles happen. That efficiency is
1.6K
Sapient Intelligence
@Sapient_Int
May 4
At Sapient Intelligence, we enable deep, efficient reasoning with our Hierarchical Reasoning Model (HRM)—a brain-inspired, latent-space architecture that moves beyond traditional, data-heavy AI. By decoupling the cognitive load, HRM uses a Slower Controller to guide abstract,
3K
Sapient Intelligence
@Sapient_Int
Apr 30
Behind the code, there is a specific kind of expertise. We are a team of researchers and engineers rooted in the labs of Tsinghua University, University of Cambridge, University of Alberta, Carnegie Mellon University, and Peking University—with experience at DeepMind, DeepSeek,
48K